phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-15 14:08:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: convert providers to be installed via package

Browse source 
currently providers have a `pip_package` list. Rather than make our own form of python dependency management, we should use `pyproject.toml` files in each provider declaring the dependencies in a more trackable manner.
Each provider can then be installed using the already in place `module` field in the ProviderSpec, pointing to the directory the provider lives in
we can then simply `uv pip install` this directory as opposed to installing the dependencies one by one

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-07-29 15:18:54 -04:00
parent 2f51273215
commit 35e17e92fa
66 changed files with 1193 additions and 67 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/datatypes.py
View file

@ -132,7 +132,6 @@ class ProviderSpec(BaseModel):
)
is_external: bool = Field(default=False, description="Notes whether this provider is an external provider.")
# used internally by the resolver; this is a hack for now
deps__: list[str] = Field(default_factory=list)
@ -182,7 +181,7 @@ A description of the provider. This is used to display in the documentation.
class InlineProviderSpec(ProviderSpec):
pip_packages: list[str] = Field(
default_factory=list,
description="The pip dependencies needed for this implementation",
description="The pip dependencies needed for this implementation (deprecated - use package_name instead)",
)
container_image: str | None = Field(
default=None,

24
llama_stack/providers/inline/agents/meta_reference/pyproject.toml Normal file
View file

@ -0,0 +1,24 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-agents-meta-reference"
version = "0.1.0"
description = "Meta's reference implementation of an agent system that can use tools, access vector databases, and perform complex reasoning tasks"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"matplotlib",
"pillow",
"pandas",
"scikit-learn",
"mcp>=1.8.1",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/inline/datasetio/localfs/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-datasetio-localfs"
version = "0.1.0"
description = "Local filesystem-based dataset I/O provider for reading and writing datasets to local storage"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"pandas",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

24
llama_stack/providers/inline/eval/meta_reference/pyproject.toml Normal file
View file

@ -0,0 +1,24 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-eval-meta-reference"
version = "0.1.0"
description = "Meta's reference implementation of evaluation tasks with support for multiple languages and evaluation metrics"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"tree_sitter",
"pythainlp",
"langdetect",
"emoji",
"nltk",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

18
llama_stack/providers/inline/files/localfs/pyproject.toml Normal file
View file

@ -0,0 +1,18 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-files-localfs"
version = "0.1.0"
description = "Local filesystem-based file storage provider for managing files and documents locally"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = []
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

29
llama_stack/providers/inline/inference/meta_reference/pyproject.toml Normal file
View file

@ -0,0 +1,29 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-meta-reference"
version = "0.1.0"
description = "Meta's reference implementation of inference with support for various model formats and optimization techniques"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"accelerate",
"fairscale",
"torch",
"torchvision",
"transformers",
"zmq",
"lm-format-enforcer",
"sentence-transformers",
"torchao==0.8.0",
"fbgemm-gpu-genai==1.1.2",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

22
llama_stack/providers/inline/inference/sentence_transformers/pyproject.toml Normal file
View file

@ -0,0 +1,22 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-sentence-transformers"
version = "0.1.0"
description = "Sentence Transformers inference provider for text embeddings and similarity search"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"torch",
"torchvision",
"sentence-transformers",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

24
llama_stack/providers/inline/post_training/huggingface/pyproject.toml Normal file
View file

@ -0,0 +1,24 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-post-training-huggingface"
version = "0.1.0"
description = "HuggingFace-based post-training provider for fine-tuning models using the HuggingFace ecosystem"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"torch",
"trl",
"transformers",
"peft",
"datasets",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

23
llama_stack/providers/inline/post_training/torchtune/pyproject.toml Normal file
View file

@ -0,0 +1,23 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-post-training-torchtune"
version = "0.1.0"
description = "TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"torch",
"torchtune==0.5.0",
"torchao==0.8.0",
"numpy",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/inline/safety/code_scanner/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-safety-code-scanner"
version = "0.1.0"
description = "Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"codeshield",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

18
llama_stack/providers/inline/safety/llama_guard/pyproject.toml Normal file
View file

@ -0,0 +1,18 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-safety-llama-guard"
version = "0.1.0"
description = "Llama Guard safety provider for content moderation and safety filtering using Meta's Llama Guard model"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = []
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/inline/safety/prompt_guard/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-safety-prompt-guard"
version = "0.1.0"
description = "Prompt Guard safety provider for detecting and filtering unsafe prompts and content"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"transformers[accelerate]",
"torch",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/inline/scoring/basic/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-scoring-basic"
version = "0.1.0"
description = "Basic scoring provider for simple evaluation metrics and scoring functions"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"requests",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/inline/scoring/braintrust/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-scoring-braintrust"
version = "0.1.0"
description = "Braintrust scoring provider for evaluation and scoring using the Braintrust platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"autoevals",
"openai",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

18
llama_stack/providers/inline/scoring/llm_as_judge/pyproject.toml Normal file
View file

@ -0,0 +1,18 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-scoring-llm-as-judge"
version = "0.1.0"
description = "LLM-as-judge scoring provider that uses language models to evaluate and score responses"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = []
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/inline/telemetry/meta_reference/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-telemetry-meta-reference"
version = "0.1.0"
description = "Meta's reference implementation of telemetry and observability using OpenTelemetry"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"opentelemetry-sdk",
"opentelemetry-exporter-otlp-proto-http",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

28
llama_stack/providers/inline/tool_runtime/rag/pyproject.toml Normal file
View file

@ -0,0 +1,28 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-tool-runtime-rag"
version = "0.1.0"
description = "RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"chardet",
"pypdf",
"tqdm",
"numpy",
"scikit-learn",
"scipy",
"nltk",
"sentencepiece",
"transformers",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/inline/vector_io/chroma/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-chroma"
version = "0.1.0"
description = "Chroma inline vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"chromadb",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/inline/vector_io/faiss/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-faiss"
version = "0.1.0"
description = "Faiss inline vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"faiss-cpu",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/inline/vector_io/milvus/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-milvus"
version = "0.1.0"
description = "Milvus inline vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"pymilvus>=2.4.10",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/inline/vector_io/qdrant/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-qdrant"
version = "0.1.0"
description = "Qdrant inline vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"qdrant-client",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/inline/vector_io/sqlite_vec/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-sqlite-vec"
version = "0.1.0"
description = "SQLite-Vec inline vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"sqlite-vec",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

1
llama_stack/providers/registry/datasetio.py
View file

@ -19,7 +19,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.datasetio,
provider_type="inline::localfs",
pip_packages=["pandas"],
module="llama_stack.providers.inline.datasetio.localfs",
config_class="llama_stack.providers.inline.datasetio.localfs.LocalFSDatasetIOConfig",
api_dependencies=[],

1
llama_stack/providers/registry/eval.py
View file

@ -13,7 +13,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.eval,
provider_type="inline::meta-reference",
pip_packages=["tree_sitter", "pythainlp", "langdetect", "emoji", "nltk"],
module="llama_stack.providers.inline.eval.meta_reference",
config_class="llama_stack.providers.inline.eval.meta_reference.MetaReferenceEvalConfig",
api_dependencies=[

36
llama_stack/providers/registry/inference.py
View file

@ -32,7 +32,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.inference,
provider_type="inline::meta-reference",
pip_packages=META_REFERENCE_DEPS,
module="llama_stack.providers.inline.inference.meta_reference",
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
description="Meta's reference implementation of inference with support for various model formats and optimization techniques.",
@ -40,10 +39,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.inference,
provider_type="inline::sentence-transformers",
pip_packages=[
"torch torchvision --index-url https://download.pytorch.org/whl/cpu",
"sentence-transformers --no-deps",
],
module="llama_stack.providers.inline.inference.sentence_transformers",
config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
description="Sentence Transformers inference provider for text embeddings and similarity search.",
@ -52,9 +47,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="cerebras",
pip_packages=[
"cerebras_cloud_sdk",
],
module="llama_stack.providers.remote.inference.cerebras",
config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
description="Cerebras inference provider for running models on Cerebras Cloud platform.",
@ -64,7 +56,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="ollama",
pip_packages=["ollama", "aiohttp", "h11>=0.16.0"],
config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
module="llama_stack.providers.remote.inference.ollama",
description="Ollama inference provider for running local models through the Ollama runtime.",
@ -74,7 +65,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="vllm",
pip_packages=["openai"],
module="llama_stack.providers.remote.inference.vllm",
config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
description="Remote vLLM inference provider for connecting to vLLM servers.",
@ -84,7 +74,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="tgi",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.remote.inference.tgi",
config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
description="Text Generation Inference (TGI) provider for HuggingFace model serving.",
@ -94,7 +83,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="hf::serverless",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.remote.inference.tgi",
config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
description="HuggingFace Inference API serverless provider for on-demand model inference.",
@ -104,7 +92,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="hf::endpoint",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.remote.inference.tgi",
config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
description="HuggingFace Inference Endpoints provider for dedicated model serving.",
@ -114,9 +101,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="fireworks",
pip_packages=[
"fireworks-ai",
],
module="llama_stack.providers.remote.inference.fireworks",
config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator",
@ -127,9 +111,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="together",
pip_packages=[
"together",
],
module="llama_stack.providers.remote.inference.together",
config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
@ -140,7 +121,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="bedrock",
pip_packages=["boto3"],
module="llama_stack.providers.remote.inference.bedrock",
config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig",
description="AWS Bedrock inference provider for accessing various AI models through AWS's managed service.",
@ -150,9 +130,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="databricks",
pip_packages=[
"openai",
],
module="llama_stack.providers.remote.inference.databricks",
config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
description="Databricks inference provider for running models on Databricks' unified analytics platform.",
@ -162,9 +139,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="nvidia",
pip_packages=[
"openai",
],
module="llama_stack.providers.remote.inference.nvidia",
config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.",
@ -174,7 +148,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="runpod",
pip_packages=["openai"],
module="llama_stack.providers.remote.inference.runpod",
config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig",
description="RunPod inference provider for running models on RunPod's cloud GPU platform.",
@ -184,7 +157,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="openai",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.openai",
config_class="llama_stack.providers.remote.inference.openai.OpenAIConfig",
provider_data_validator="llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator",
@ -195,7 +167,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="anthropic",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.anthropic",
config_class="llama_stack.providers.remote.inference.anthropic.AnthropicConfig",
provider_data_validator="llama_stack.providers.remote.inference.anthropic.config.AnthropicProviderDataValidator",
@ -206,7 +177,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="gemini",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.gemini",
config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig",
provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator",
@ -217,7 +187,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="vertexai",
pip_packages=["litellm", "google-cloud-aiplatform"],
module="llama_stack.providers.remote.inference.vertexai",
config_class="llama_stack.providers.remote.inference.vertexai.VertexAIConfig",
provider_data_validator="llama_stack.providers.remote.inference.vertexai.config.VertexAIProviderDataValidator",
@ -247,7 +216,6 @@ Available Models:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="groq",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.groq",
config_class="llama_stack.providers.remote.inference.groq.GroqConfig",
provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator",
@ -258,7 +226,6 @@ Available Models:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="llama-openai-compat",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.llama_openai_compat",
config_class="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaCompatConfig",
provider_data_validator="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator",
@ -269,7 +236,6 @@ Available Models:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="sambanova",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.sambanova",
config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator",
@ -280,7 +246,6 @@ Available Models:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="passthrough",
pip_packages=[],
module="llama_stack.providers.remote.inference.passthrough",
config_class="llama_stack.providers.remote.inference.passthrough.PassthroughImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.passthrough.PassthroughProviderDataValidator",
@ -291,7 +256,6 @@ Available Models:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="watsonx",
pip_packages=["ibm_watson_machine_learning"],
module="llama_stack.providers.remote.inference.watsonx",
config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig",
provider_data_validator="llama_stack.providers.remote.inference.watsonx.WatsonXProviderDataValidator",

3
llama_stack/providers/registry/post_training.py
View file

@ -13,7 +13,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.post_training,
provider_type="inline::torchtune",
pip_packages=["torch", "torchtune==0.5.0", "torchao==0.8.0", "numpy"],
module="llama_stack.providers.inline.post_training.torchtune",
config_class="llama_stack.providers.inline.post_training.torchtune.TorchtunePostTrainingConfig",
api_dependencies=[
@ -25,7 +24,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.post_training,
provider_type="inline::huggingface",
pip_packages=["torch", "trl", "transformers", "peft", "datasets"],
module="llama_stack.providers.inline.post_training.huggingface",
config_class="llama_stack.providers.inline.post_training.huggingface.HuggingFacePostTrainingConfig",
api_dependencies=[
@ -38,7 +36,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.post_training,
adapter=AdapterSpec(
adapter_type="nvidia",
pip_packages=["requests", "aiohttp"],
module="llama_stack.providers.remote.post_training.nvidia",
config_class="llama_stack.providers.remote.post_training.nvidia.NvidiaPostTrainingConfig",
description="NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform.",

4
llama_stack/providers/registry/safety.py
View file

@ -30,7 +30,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.safety,
provider_type="inline::llama-guard",
pip_packages=[],
module="llama_stack.providers.inline.safety.llama_guard",
config_class="llama_stack.providers.inline.safety.llama_guard.LlamaGuardConfig",
api_dependencies=[
@ -52,7 +51,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.safety,
adapter=AdapterSpec(
adapter_type="bedrock",
pip_packages=["boto3"],
module="llama_stack.providers.remote.safety.bedrock",
config_class="llama_stack.providers.remote.safety.bedrock.BedrockSafetyConfig",
description="AWS Bedrock safety provider for content moderation using AWS's safety services.",
@ -62,7 +60,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.safety,
adapter=AdapterSpec(
adapter_type="nvidia",
pip_packages=["requests"],
module="llama_stack.providers.remote.safety.nvidia",
config_class="llama_stack.providers.remote.safety.nvidia.NVIDIASafetyConfig",
description="NVIDIA's safety provider for content moderation and safety filtering.",
@ -72,7 +69,6 @@ def available_providers() -> list[ProviderSpec]:
api=Api.safety,
adapter=AdapterSpec(
adapter_type="sambanova",
pip_packages=["litellm", "requests"],
module="llama_stack.providers.remote.safety.sambanova",
config_class="llama_stack.providers.remote.safety.sambanova.SambaNovaSafetyConfig",
provider_data_validator="llama_stack.providers.remote.safety.sambanova.config.SambaNovaProviderDataValidator",

3
llama_stack/providers/registry/scoring.py
View file

@ -13,7 +13,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.scoring,
provider_type="inline::basic",
pip_packages=["requests"],
module="llama_stack.providers.inline.scoring.basic",
config_class="llama_stack.providers.inline.scoring.basic.BasicScoringConfig",
api_dependencies=[
@ -25,7 +24,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.scoring,
provider_type="inline::llm-as-judge",
pip_packages=[],
module="llama_stack.providers.inline.scoring.llm_as_judge",
config_class="llama_stack.providers.inline.scoring.llm_as_judge.LlmAsJudgeScoringConfig",
api_dependencies=[
@ -38,7 +36,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.scoring,
provider_type="inline::braintrust",
pip_packages=["autoevals", "openai"],
module="llama_stack.providers.inline.scoring.braintrust",
config_class="llama_stack.providers.inline.scoring.braintrust.BraintrustScoringConfig",
api_dependencies=[

5
llama_stack/providers/registry/tool_runtime.py
View file

@ -41,7 +41,6 @@ def available_providers() -> list[ProviderSpec]:
adapter_type="brave-search",
module="llama_stack.providers.remote.tool_runtime.brave_search",
config_class="llama_stack.providers.remote.tool_runtime.brave_search.config.BraveSearchToolConfig",
pip_packages=["requests"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.brave_search.BraveSearchToolProviderDataValidator",
description="Brave Search tool for web search capabilities with privacy-focused results.",
),
@ -52,7 +51,6 @@ def available_providers() -> list[ProviderSpec]:
adapter_type="bing-search",
module="llama_stack.providers.remote.tool_runtime.bing_search",
config_class="llama_stack.providers.remote.tool_runtime.bing_search.config.BingSearchToolConfig",
pip_packages=["requests"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.bing_search.BingSearchToolProviderDataValidator",
description="Bing Search tool for web search capabilities using Microsoft's search engine.",
),
@ -63,7 +61,6 @@ def available_providers() -> list[ProviderSpec]:
adapter_type="tavily-search",
module="llama_stack.providers.remote.tool_runtime.tavily_search",
config_class="llama_stack.providers.remote.tool_runtime.tavily_search.config.TavilySearchToolConfig",
pip_packages=["requests"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.tavily_search.TavilySearchToolProviderDataValidator",
description="Tavily Search tool for AI-optimized web search with structured results.",
),
@ -74,7 +71,6 @@ def available_providers() -> list[ProviderSpec]:
adapter_type="wolfram-alpha",
module="llama_stack.providers.remote.tool_runtime.wolfram_alpha",
config_class="llama_stack.providers.remote.tool_runtime.wolfram_alpha.config.WolframAlphaToolConfig",
pip_packages=["requests"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.wolfram_alpha.WolframAlphaToolProviderDataValidator",
description="Wolfram Alpha tool for computational knowledge and mathematical calculations.",
),
@ -85,7 +81,6 @@ def available_providers() -> list[ProviderSpec]:
adapter_type="model-context-protocol",
module="llama_stack.providers.remote.tool_runtime.model_context_protocol",
config_class="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderConfig",
pip_packages=["mcp>=1.8.1"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderDataValidator",
description="Model Context Protocol (MCP) tool for standardized tool calling and context management.",
),

12
llama_stack/providers/registry/vector_io.py
View file

@ -19,7 +19,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.vector_io,
provider_type="inline::meta-reference",
pip_packages=["faiss-cpu"],
module="llama_stack.providers.inline.vector_io.faiss",
config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
deprecation_warning="Please use the `inline::faiss` provider instead.",
@ -30,7 +29,6 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.vector_io,
provider_type="inline::faiss",
pip_packages=["faiss-cpu"],
module="llama_stack.providers.inline.vector_io.faiss",
config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
api_dependencies=[Api.inference],
@ -83,7 +81,6 @@ more details about Faiss in general.
InlineProviderSpec(
api=Api.vector_io,
provider_type="inline::sqlite-vec",
pip_packages=["sqlite-vec"],
module="llama_stack.providers.inline.vector_io.sqlite_vec",
config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
api_dependencies=[Api.inference],
@ -290,7 +287,6 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f
InlineProviderSpec(
api=Api.vector_io,
provider_type="inline::sqlite_vec",
pip_packages=["sqlite-vec"],
module="llama_stack.providers.inline.vector_io.sqlite_vec",
config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
deprecation_warning="Please use the `inline::sqlite-vec` provider (notice the hyphen instead of underscore) instead.",
@ -304,7 +300,6 @@ Please refer to the sqlite-vec provider documentation.
Api.vector_io,
AdapterSpec(
adapter_type="chromadb",
pip_packages=["chromadb-client"],
module="llama_stack.providers.remote.vector_io.chroma",
config_class="llama_stack.providers.remote.vector_io.chroma.ChromaVectorIOConfig",
description="""
@ -347,7 +342,6 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
InlineProviderSpec(
api=Api.vector_io,
provider_type="inline::chromadb",
pip_packages=["chromadb"],
module="llama_stack.providers.inline.vector_io.chroma",
config_class="llama_stack.providers.inline.vector_io.chroma.ChromaVectorIOConfig",
api_dependencies=[Api.inference],
@ -391,7 +385,6 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
Api.vector_io,
AdapterSpec(
adapter_type="pgvector",
pip_packages=["psycopg2-binary"],
module="llama_stack.providers.remote.vector_io.pgvector",
config_class="llama_stack.providers.remote.vector_io.pgvector.PGVectorVectorIOConfig",
description="""
@ -430,7 +423,6 @@ See [PGVector's documentation](https://github.com/pgvector/pgvector) for more de
Api.vector_io,
AdapterSpec(
adapter_type="weaviate",
pip_packages=["weaviate-client"],
module="llama_stack.providers.remote.vector_io.weaviate",
config_class="llama_stack.providers.remote.vector_io.weaviate.WeaviateVectorIOConfig",
provider_data_validator="llama_stack.providers.remote.vector_io.weaviate.WeaviateRequestProviderData",
@ -471,7 +463,6 @@ See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more
InlineProviderSpec(
api=Api.vector_io,
provider_type="inline::qdrant",
pip_packages=["qdrant-client"],
module="llama_stack.providers.inline.vector_io.qdrant",
config_class="llama_stack.providers.inline.vector_io.qdrant.QdrantVectorIOConfig",
api_dependencies=[Api.inference],
@ -524,7 +515,6 @@ See the [Qdrant documentation](https://qdrant.tech/documentation/) for more deta
Api.vector_io,
AdapterSpec(
adapter_type="qdrant",
pip_packages=["qdrant-client"],
module="llama_stack.providers.remote.vector_io.qdrant",
config_class="llama_stack.providers.remote.vector_io.qdrant.QdrantVectorIOConfig",
description="""
@ -538,7 +528,6 @@ Please refer to the inline provider documentation.
Api.vector_io,
AdapterSpec(
adapter_type="milvus",
pip_packages=["pymilvus>=2.4.10"],
module="llama_stack.providers.remote.vector_io.milvus",
config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig",
description="""
@ -739,7 +728,6 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi
InlineProviderSpec(
api=Api.vector_io,
provider_type="inline::milvus",
pip_packages=["pymilvus>=2.4.10"],
module="llama_stack.providers.inline.vector_io.milvus",
config_class="llama_stack.providers.inline.vector_io.milvus.MilvusVectorIOConfig",
api_dependencies=[Api.inference],

20
llama_stack/providers/remote/datasetio/huggingface/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-datasetio-huggingface"
version = "0.1.0"
description = "HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"datasets",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/datasetio/nvidia/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-datasetio-nvidia"
version = "0.1.0"
description = "NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"datasets",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/eval/nvidia/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-eval-nvidia"
version = "0.1.0"
description = "NVIDIA's evaluation provider for running evaluation tasks on NVIDIA's platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"requests",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/anthropic/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-anthropic"
version = "0.1.0"
description = "Anthropic inference provider for accessing Claude models and Anthropic's AI services"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"litellm",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/bedrock/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-bedrock"
version = "0.1.0"
description = "AWS Bedrock inference provider for accessing various AI models through AWS's managed service"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"boto3",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/cerebras/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-cerebras"
version = "0.1.0"
description = "Cerebras inference provider for running models on Cerebras Cloud platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"cerebras_cloud_sdk",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/databricks/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-databricks"
version = "0.1.0"
description = "Databricks inference provider for running models on Databricks' unified analytics platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"openai",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/fireworks/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-fireworks"
version = "0.1.0"
description = "Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"fireworks-ai",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/gemini/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-gemini"
version = "0.1.0"
description = "Google Gemini inference provider for accessing Gemini models and Google's AI services"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"litellm",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/groq/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-groq"
version = "0.1.0"
description = "Groq inference provider for ultra-fast inference using Groq's LPU technology"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"litellm",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/llama_openai_compat/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-llama-openai-compat"
version = "0.1.0"
description = "Llama OpenAI-compatible provider for using Llama models with OpenAI API format"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"litellm",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/nvidia/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-nvidia"
version = "0.1.0"
description = "NVIDIA inference provider for accessing NVIDIA NIM models and AI services"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"openai",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

23
llama_stack/providers/remote/inference/ollama/pyproject.toml Normal file
View file

@ -0,0 +1,23 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-ollama"
version = "0.1.0"
description = "Ollama inference provider for running local models through the Ollama runtime"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"ollama",
"aiohttp",
"h11>=0.16.0",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/openai/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-openai"
version = "0.1.0"
description = "OpenAI inference provider for accessing GPT models and other OpenAI services"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"litellm",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/inference/passthrough/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-passthrough"
version = "0.1.0"
description = "Passthrough inference provider for connecting to any external inference service not directly supported"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/runpod/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-runpod"
version = "0.1.0"
description = "RunPod inference provider for running models on RunPod's cloud GPU platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"openai",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/sambanova/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-sambanova"
version = "0.1.0"
description = "SambaNova inference provider for running models on SambaNova's dataflow architecture"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"litellm",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

22
llama_stack/providers/remote/inference/tgi/pyproject.toml Normal file
View file

@ -0,0 +1,22 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-tgi"
version = "0.1.0"
description = "Text Generation Inference (TGI) provider for HuggingFace model serving"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"huggingface_hub",
"aiohttp",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/together/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-together"
version = "0.1.0"
description = "Together AI inference provider for open-source models and collaborative AI development"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"together",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

19
llama_stack/providers/remote/inference/vertexai/pyproject.toml Normal file
View file

@ -0,0 +1,19 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-vertexai"
version = "0.1.0"
description = "Google VertexAI Remote Inference Provider"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"litellm",
"google-cloud-aiplatform"
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/vllm/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-vllm"
version = "0.1.0"
description = "Remote vLLM inference provider for connecting to vLLM servers"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"openai",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/inference/watsonx/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-inference-watsonx"
version = "0.1.0"
description = "IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"ibm_watson_machine_learning",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/post_training/nvidia/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-post-training-nvidia"
version = "0.1.0"
description = "NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"requests",
"aiohttp",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/safety/bedrock/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-safety-bedrock"
version = "0.1.0"
description = "AWS Bedrock safety provider for content moderation using AWS's safety services"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"boto3",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/safety/nvidia/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-safety-nvidia"
version = "0.1.0"
description = "NVIDIA's safety provider for content moderation and safety filtering"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"requests",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

21
llama_stack/providers/remote/safety/sambanova/pyproject.toml Normal file
View file

@ -0,0 +1,21 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-safety-sambanova"
version = "0.1.0"
description = "SambaNova's safety provider for content moderation and safety filtering"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"litellm",
"requests",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/tool_runtime/bing_search/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-tool-runtime-bing-search"
version = "0.1.0"
description = "Bing Search tool for web search capabilities using Microsoft's search engine"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"requests",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/tool_runtime/brave_search/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-tool-runtime-brave-search"
version = "0.1.0"
description = "Brave Search tool for web search capabilities with privacy-focused results"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"requests",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/tool_runtime/model_context_protocol/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-tool-runtime-model-context-protocol"
version = "0.1.0"
description = "Model Context Protocol (MCP) tool for standardized tool calling and context management"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"mcp>=1.8.1",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/tool_runtime/tavily_search/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-tool-runtime-tavily-search"
version = "0.1.0"
description = "Tavily Search tool for AI-optimized web search with structured results"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"requests",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/tool_runtime/wolfram_alpha/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-tool-runtime-wolfram-alpha"
version = "0.1.0"
description = "Wolfram Alpha tool for computational knowledge and mathematical calculations"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"requests",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/vector_io/chroma/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-chroma-remote"
version = "0.1.0"
description = "Chroma remote vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"chromadb-client",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/vector_io/milvus/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-milvus-remote"
version = "0.1.0"
description = "Milvus remote vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"pymilvus>=2.4.10",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/vector_io/pgvector/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-pgvector"
version = "0.1.0"
description = "PGVector remote vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"psycopg2-binary",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/vector_io/qdrant/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-qdrant-remote"
version = "0.1.0"
description = "Qdrant remote vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"qdrant-client",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]

20
llama_stack/providers/remote/vector_io/weaviate/pyproject.toml Normal file
View file

@ -0,0 +1,20 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "llama-stack-provider-vector-io-weaviate"
version = "0.1.0"
description = "Weaviate remote vector database provider for Llama Stack"
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
requires-python = ">=3.12"
license = { "text" = "MIT" }
dependencies = [
"weaviate-client",
]
[tool.setuptools.packages.find]
where = ["."]
include = ["llama_stack*"]